Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 4496
    Prev
    Next
    INDEX
    Explanations

    sentences using phrases related to reminding or emphasizing a point

    oai_token-act-pair · gpt-3.5-turbo

    phrases that emphasize the importance of clarification or caution in communication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ieu
    -0.71
    tnc
    -0.69
    SPONSORED
    -0.65
    rouse
    -0.64
    anooga
    -0.62
    igent
    -0.62
    itu
    -0.62
    Hide
    -0.62
    iasm
    -0.61
    hello
    -0.61
    POSITIVE LOGITS
     NEVER
    1.27
     ALSO
    1.25
     ONLY
    1.18
     actually
    1.10
     ALWAYS
    1.05
     NOT
    1.05
     VERY
    0.97
     BEFORE
    0.94
     DOES
    0.93
     DID
    0.91
    Activations Density 0.767%

    No Known Activations